Attaché: Towards Ideal Memory Compression by Mitigating Metadata Bandwidth Overheads

Attaché: Towards Ideal Memory Compression by Mitigating Metadata Bandwidth Overheads
复制标题

附件:通过减少元数据带宽开销实现理想的内存压缩

DOI:
10.1109/micro.2018.00034
复制
发表时间:
2018
期刊:
2018 51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)
影响因子:
--
通讯作者:
Michael B. Healy
Michael B. Healy
中科院分区:
--
文献类型:
--
作者:
Seokin Hong;Prashant J. Nair;B. Abali;A. Buyuktosunoglu;Kyu;Michael B. Healy

文献摘要

被引文献

相似文献

存储系统变得带宽受限,数据压缩被视为增加其有效带宽的一种简单技术。然而,数据压缩需要访问元数据,这会产生额外的带宽开销。即使在使用元数据缓存之后,元数据的带宽开销也会降低压缩的好处。本文提出了一种减少元数据访问开销的框架Attaché。附加框架由两个组成部分组成。第一个组件称为混合元数据引擎(BLEM),它允许一起访问数据及其元数据。BLEM只需额外访问0.003倍的元数据,并且几乎消除了所有元数据带宽开销。第二个组件称为压缩预判断器(COPR),它预测内存块是否被压缩。COPR预测器使用细粒度的行级预测器、粗粒度的页级预测器和全局指示器。这使得Attaché能够在发送内存读取请求之前预测内存块的可压缩性。我们在一个使用子排名的存储系统上实现了Attaché。平均而言,与不使用数据压缩的基准系统相比,Attaché实现了15.3%的加速(理想17%)和22%的能耗(理想23%)。Attaché完全基于硬件,仅使用368KB的SRAM。
Memory systems are becoming bandwidth constrained and data compression is seen as a simple technique to increase their effective bandwidth. However, data compressionrequires accessing Metadata which incurs additional bandwidth overheads. Even after using a Metadata-Cache, the bandwidth overheads of Metadata can reduce the benefits of compression. This paper proposes Attaché, a framework that reduces the overheads of Metadata accesses. The Attaché framework consists of two components. The first component, called the Blended Metadata Engine (BLEM), enables data and its Metadata to be accessed together. BLEM incurs additional Metadata accesses only 0.003% times and removes almost all Metadata bandwidth overheads. The second component, called theCompression Pre-dictor(COPR), predicts if the memory block is compressed. TheCOPR predictor uses a fine-grained line-level predictor, a coarse-grained page-level predictor, and a global indicator. This enables Attaché to predict the compressibility of the memory block before sending a memory read request. We implement Attaché on a memory system that uses Sub-Ranking. On average, Attaché achieves 15.3% speedup (ideal 17%) and saves 22% energy consumption (ideal 23%) when compared to a baseline system that does not employ data compression. Attaché is completely hardware-based and uses only 368KB of SRAM.